检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2025年第5期49卷 37-48页

作者： Remmach, Hassnae Razak, Siti Fatimah Abdul Ullah, Arif Yogarayan, Sumendra Sayeed, Md Shohel Mrhari, Amine Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh40000 Morocco Faculty of Information Science and Technology Multimedia University Ayer Keroh75450 Malaysia Research in Computer Science Laboratory Faculty of Sciences Ibn Tofail University Kenitra Morocco

In a number of industries, including computer graphics, robotics, and medical imaging, three-dimensional reconstruction is essential. In this research, a CNN-based Multi-output and Multi-Task Regressor with deep learning capabilities is proposed for three-dimensional object reconstruction from 3D point cloud. Our approach is grounded in the original Point Net architecture, which addresses the difficulties associated with convolution when applied to point clouds. Firstly, this paper is modified using a Multi-Output Regressor to accurately recreate Super forms from 3D point clouds. Using this method, we first extract features from the 3D point cloud using Point Net. After that, a Multi-Output Regressor receives these data and uses them to anticipate the Super shape parameters needed to reconstruct the shape. Taking in the data, the Multi-Output Regressor retrieved characteristics from Point Net and simultaneously predicts several outcomes. Second, a Multi-Task Regressor is used to modify the Point Net. The network gains from the capacity to transfer knowledge from one task to another, improving the model's overall performance. The model would forecast the ten parameters needed to create the shape in the case of rebuilding Super shapes. The test findings were better than expected;they are intriguing in terms of prediction accuracy and cost, and they update the result by 80%, which is a good accomplishment for the study. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Mel-Frequency Cepstrum Coefficients and Gated Recurrent Units Approach for Voiceprint Recognition 24

A Hybrid Mel-Frequency Cepstrum Coefficients and Gated Recur...

引用

8th International Conference on Advances in Artificial Intelligence, ICAAI 2024

作者： Teng, Jackson Horlick Ong, Thian Song Lim, Kian Ming Faculty of Information Science and Technology Multimedia University Melaka Malaysia School of Computer Science University of Nottingham Ningbo China

ISBN: (纸本)9798400718014

A voiceprint system recognizes an individual using their voice biometrics for person recognition purpose. Voiceprint offers notable advantages in convenience and cost since it only requires a microphone, a ubiquitous component in smartphones, making it highly practical for user identity management such as personalized customer support by recognizing the user using just their voice. This paper proposes a voiceprint recognition system to combine Mel-Frequency Cepstrum Coefficients (MFCC) and Gated Recurrent Units (GRU), which is termed MFCC-GRU method. The resulting mixture is extremely useful in voiceprint recognition, as it could accurately capture and evaluate the unique characteristics and temporal dynamics of an individual’s voice for identity verification. The proposed method is tested on three voiceprint datasets and achieving the highest accuracy of 98.17% at best. © 2024 Copyright held by the owner/author(s).

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

引用

computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

An Agricultural Sentiment Dataset for Pest Control and Crop Diseases 3rd

An Agricultural Sentiment Dataset for Pest Control and Cro...

引用

3rd International Conference on Language Processing and Knowledge Management, LPKM 2024

作者： Chamekh, Ameni Mahfoudh, Mariem Boukadi, Khouloud MIRACL Laboratory Sfax Tunisia Faculty of Economics and Management of Sfax Sfax Tunisia Higher Institute of Computer Science and Multimedia of Sfax Sakiet Ezzit Tunisia

ISBN: (纸本)9783031850660

This paper focuses on creating a dataset in an agricultural domain to understand and analyze sentiments related to pesticides, pests and crop disease. Collecting data allows us to gain insights into the opinions, attitudes, and experiences of farmers, agricultural experts, and consumers. Therefore, we collected data from social media and online platforms based on a list of keywords extracted from the AGROVOC multilingual controlled thesaurus. We have obtained two datasets: the first comprises 1617 tweets regarding pests and crop diseases from Twitter, while the second consists of 10 181 reviews on pesticide products from Amazon. Aspect extraction has been employed, identifying and extracting specific features or aspects discussed in reviews or tweets. This process enables a more granular and detailed data analysis by allowing us to go deeper into the data and understand the sentiment associated with each aspect rather than the overall sentiment. We identified eight aspects within the Amazon dataset, including "price", "package", "toxicity", etc. Similarly, we extracted relevant aspects from our Twitter dataset, resulting in five aspects such as: "pests", "safety", "toxicity", etc. Then, the data will be pre-annotated in collaboration with agricultural domain experts from INAT. This data will be used for future analyses and will inform the purchasing decisions of various decision-makers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

MobileViTv2-MLP: Arabic Traffic Sign Recognition with Enhanced Lightweight Vision Transformers 17

MobileViTv2-MLP: Arabic Traffic Sign Recognition with Enhanc...

引用

17th International Conference on Machine Vision, ICMV 2024

作者： Alqahtani, A. Alqaysi, E. Alsarhani, W. Lee, C.P. Alsharafi, A. Alzahrani, M. Almosa, A. Computer Science Department King Khalid University Saudi Arabia King Khalid University Saudi Arabia Faculty of Information Science and Technology Multimedia University Malaysia English Department King Khalid University Saudi Arabia

ISBN: (纸本)9781510688278

Traffic Sign Recognition (TSR) plays a pivotal role in advanced driver-assistance systems (ADAS) and autonomous vehicles, serving as a fundamental element for safe and efficient road navigation. Due to a diverse array of factors such as variations in sign appearance, fluctuating lighting conditions, occlusions, and environmental influences, the task of TSR poses significant challenges. These challenges have been addressed with advanced deep learning techniques, particularly with Convolutional Neural Networks (CNNs) and other architectures proficient in handling visual data. While such approaches have shown promise, they are often limited in their ability to effectively manage the aforementioned challenges. To overcome these obstacles, we propose a novel approach called the MobileViTv2-MLP method. This approach aims to develop a resilient model specifically tailored to the task of identifying and categorizing traffic signs encountered during driving. Our methodology involves training the model on an extensive dataset comprising diverse representations of traffic signs under varying conditions, ensuring its adaptability and reliability in real-world scenarios. Through experimentation and evaluation, our refined approach has demonstrated exceptional accuracy, achieving a remarkable 99.75%. This outcome underscores the robustness and effectiveness of our proposed method in addressing the challenges inherent in TSR, thereby contributing to the advancement of intelligent transportation systems. © 2025 SPIE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Encoding laparoscopic image to words using vision transformer for distortion classification and ranking in laparoscopic videos

引用

multimedia Tools and Applications 2025年第10期84卷 7159-7181页

作者： AlDahoul, Nouar Karim, Hezerul Abdul Momo, Mhd Adel Tan, Myles Joshua Toledo Fermin, Jamie Ledesma Faculty of Engineering Multimedia University Cyberjaya63100 Malaysia Computer Science New York University Abu Dhabi United Arab Emirates College of Engineering and Technology University of St. La Salle Bacolod6100 Philippines Department of Natural Sciences University of St. La Salle Bacolod6100 Philippines

Laparoscopic videos are tools used by surgeons to insert narrow tubes into the abdomen and keep the skin without large incisions. The videos captured by a camera are prone to numerous distortions such as uneven illumination, motion blur, defocus blur, smoke, and noise which have impact on visual quality. Automatic detection and identification of distortions are significant to enhance the quality of laparoscopic videos to avoid errors during surgery. The video quality assessment includes two stages: classification of distortions affecting the video frames to identify their types and ranking of distortions to estimate the intensity levels. The dataset generated in ICIP2020 challenge including laparoscopic videos was utilized for training, validation, and testing the proposed solution. The difficulty of this dataset is caused by having five categories of distortions and four levels of severity. Additionally, the availability of multiple distortion categories in one video is considered the most challenging part of this dataset. The work presented in this paper contributes to solve the multi-label distortion classification and ranking problem. This paper aims to enhance the performance of distortion classification solutions. Vision transformer which is a deep learning model was used to extract informative features by transferring learning and representation from the general domain to the medical domain (laparoscopic videos). Additionally, six parallel multilayer perceptron (MLP) classifiers were added and attached to vision transformer for distortion classification and ranking. The experiment showed that the proposed solution outperforms existing distortion classification methods in terms of average accuracy (89.7%), average single distortion F1 score (94.18%), and average of both single and multiple distortions F1 score (96.86%). Moreover, it can also rank the distortions with an average accuracy of 79.22% and average F1 score of 78.44%. Hence, the high performance of t

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Adaptive resource allocation and routing for integrated sensing and communications for wireless technologies

引用

Eurasip Journal on Wireless Communications and Networking 2025年第1期2025卷 1-27页

作者： Subramaniyan, Manochandar Venkatasamy, Thiruppathy Kesavan Thotakuruchi Mathiyalagan, Nithya Jakir Hossen, Md. Faculty of Digital Business & Analytics Bharathidasan Institute of Management Tamil Nadu Tiruchirappalli 620014 India Faculty of Information Technology Dhanalakshmi Srinivasan Engineering College Tamil Nadu Perambalur 621212 India Center for Advanced Analytics (CAA) COE for Artificial Intelligence Faculty of Engineering & Technology (FET) Multimedia University Melaka 75450 Malaysia Faculty of Computer Science and Engineering K. Ramakrishnan College of Engineering Tamil Nadu Samayapuram 621112 India Post Doctoral Fellow Department of Engineering & Technology Multimedia University Melaka 75450 Malaysia

The integrated sensing and communications (ISC) application completely changes the game regarding collecting, analyzing, and dispensing facts in real time via combining sensing skills with communication structure. The present research delves into how ISC can enhance decision-making in healthcare, smart towns, and environmental monitoring. Issues with interoperability, electricity intake, ecological resilience, and the worrying latency requirements of task-critical packages are many obstacles to easy integration. Our proposed mechanism, adaptive resource allocation and routing for integrated sensing (ARAR-IS), which uses new wireless technologies, attempts to clear up these problems by allocating and routing assets for incorporated sensing. ARAR-IS dynamically allocates sources and routes information considering the real global and network dynamics. Optimizing resource utilization, mitigating interference, and enhancing dependability in ISC systems are achieved using ARAR-IS, which leverages cognitive routing algorithms and software program-defined networking ideas. With ARAR-IS, various computer-aided engineering regions can benefit from customized remedy plans, far-off patient tracking, and real-time attempts to lessen pollution. These domains include healthcare, proper infrastructure, industrial automation, and environmental monitoring. Thorough simulation-based assessments show that ARAR-IS is a pleasant alternative for ISC systems in many one-of-a-kind situations because of its high reliability, low-strength intake, excessive throughput, and low latency. © The Author(s) 2025.

关键词： Adaptive control Data communication Resource allocation Routing protocols Wireless channels

来源：评论

学校读者我要写书评

暂无评论

MDR-LOD2 Model: Forgery Detection using Modified Depth ResNet features and Layer Optimized Dunnock Deep Model from Videos

引用

computers and Electrical Engineering 2025年 125卷

作者： Ugale, Meena Midhunchakkaravarthy, J. Department of Computer Science and Multimedia Lincoln University College Kuala Lumpur 47301 Malaysia Faculty of Computer Science and Multimedia Lincoln University College Kuala Lumpur 47301 Malaysia

Digital forgery detection implies the identification of any modifications or manipulation of the digital content, typically image, video, or document, to confirm their authenticity. Consequently, this contribution seeks to address the challenges experienced by existing techniques by introducing the Modified DepthResNet descriptor and Layer Optimized Dunnock Deep model (MDR-LOD2) model. MDR descriptor is proficient at generating features in ResNet architecture and hence it helps in the fusion of a DepthNet to detect depth-related cues which plays a crucial role in spotting forgery. More specifically, the MDR descriptor captures the subtle details via the spatial connections and depth perception, resulting in boosting the detection performance. The hybrid optimizer strategy combines meticulous exploration and dynamic adaptation together increasing the model's ability to detect splicing forgery. The proposed approach exploits the LOD2 architecture well suited for capturing the temporal aspects and effectively analyzes the intricate patterns of video data. Additionally, the LOD2 model is enabled with the Dunnock Hunt Optimization (DHO) algorithm for layer optimization facilitating optimal performance of every layer in LSTM. Moreover, the integration of LOD2 and MDR descriptor in conjunction with the DHO algorithm in the proposed approach assist in identifying the forged regions in the video frames. The experimental results demonstrate that the proposed approach attains an accuracy of 98.54 %, sensitivity of 98.54 %, specificity of 98.53 %, and F1-score of 98.54 % for DSO-1. For DSI-1 DTS, the proposed approach achieves remarkable results with high accuracy of 98.47 %, sensitivity of 98.41 %, specificity of 98.52 %, and F1-score of 98.47 %. Finally, the proposed model obtained the remarkable results for the Face Forensics database achieving high accuracy of 97.83 %, sensitivity of 97.76 %, specificity of 97.89 %, and F1-score of 97.83 % outperforming other existing techn

关键词： Deep learning Digital forensics Dunnock hunt optimization Image manipulation Video forgery detection

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of UHF RFID Tags Mounted on PET Liquid Containers Subjected to External Forces

Experimental Analysis of UHF RFID Tags Mounted on PET Liquid...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Pol Brunet Mohammed Alsultan Joan Melià-Seguí Sergio López-Soriano Internet Interdisciplinary Institute Universitat Oberta de Catalunya (UOC) Spain Faculty of Computer Science Multimedia and Telecommunications of the UOC Spain

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

This paper presents the design of a battery-free UHF RFID tag for fluid-based sensing applications. The proposed system utilizes a polyethylene terephthalate (PET) container as the antenna substrate, which is filled with a mixture of three fluids: air, water and oil. A vibration detection RFID sensor is implemented by exploiting changes in the tag antenna's input impedance caused by variations in the state of the fluids within the PET container. These variations are captured using a self-tuning integrated circuit (IC). The method is initially validated through experiments involving a microstrip transmission line (TL) and an RFID tag. In the experiment, the fluid container is shaken to mix the fluids, inducing changes in the dielectric properties of the substrate. These changes are analyzed using S-parameter measurements for the TL and sensor code readings for the self-tuning RFID IC. The experimental results demonstrate the sensor's ability to continuously monitor fluid state changes during the relaxation process following an initial disturbance. This study highlights the potential of the proposed approach for real-time fluid state monitoring in sensing applications.

关键词： Vibrations Microwave antennas Liquids Oils Containers Transmission line measurements Sensors RFID tags Substrates Monitoring

来源：评论

学校读者我要写书评

暂无评论

Efficient Temporal Data Mining Technique Using Dynamic Time Warped LSTM for E-Commerce Recommendation Systems 3rd

Efficient Temporal Data Mining Technique Using Dynamic Time ...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Rajassekharan, Dinesh Subramanian, Jayasundar Lazar, Arokia Jesu Prabhu Pichuka Veera Venkata Satya, Srinivas Ray, Samrat Ammasai, Viswanathan Sengan, Sudhakar Faculty of AI Computing and Multimedia Lincoln University College Petaling Jaya47301 Malaysia Department of Computer Science and Engineering Idhaya Engineering College For Women Tamil Nadu Chinnasalem606201 India Department of Computer Science and Engineering CMR Institute of Technology Hyderabad501401 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Dean Head of International Relations IIMS Pune411033 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627451 India

ISBN: (纸本)9789819783540

The rapid surge of the electronic commerce (Ecomm) industry has ushered in intensified competition, with platforms vying for customer attention and loyalty. Many Ecomm sites have been employing various tactics to stand out, with Recommendation Systems (RS at the forefront of their strategies. However, traditional RS faces challenges, mainly when interactions occur at irregular intervals. This article introduces the DTW + LSTM framework, a methodology combining the merits of Long Short-Term Memory Networks and Dynamic Time Warping to improve this work. This method requires consideration of DTW's time series data alignment capabilities to account for interaction interval variability. The LSTM is then designed to accurately record the key elements of user interactions in sequential order. Combining the outcomes of these two methodologies in the DTW + LSTM model presents a more flexible and extensive approach to generating online shopping recommendations. The design guarantees that forecasts continue to be reliable and accurate despite the inherent temporal deviations that can be observed in user data. This paper investigates the context of this approach, its benefits, and prospective developments, demonstrating its possibilities in the dynamic Ecomm market. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Accuracy CNN E-commerce F1-score GRU LSTM Machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：